AMD Ryzen AI Max 390 vs Intel Core Ultra X9 378H Comparison

The AMD Ryzen AI Max 390 and Intel Core Ultra X9 378H represent two distinct approaches to high-performance mobile computing. The recorded data shows the AMD part winning 11 of the 17 direct benchmark comparisons, while the Intel chip secures 6 wins. The AMD Ryzen AI Max 390 leads in overall average benchmark score with 56273 points against 47468 for the Intel Core Ultra X9 378H, placing it in the 91st percentile of all CPUs compared to the Intel part’s 89th percentile. These scores position the AMD processor slightly ahead of the AMD Ryzen AI 9 HX PRO 470 and Intel Core i9-14900HX, while the Intel chip trades blows with the Intel Core i7-13700KF and Intel Core i9-12900F.

Where Each One Wins

The AMD Ryzen AI Max 390 dominates in multi-threaded rendering and integer-heavy workloads. Its Cinebench R23 multicore score of 36064 exceeds the Intel Core Ultra X9 378H’s 32553 by 10.8 percent, a consistent margin replicated across R15, R20, and R23 runs. The PassMark integer math test shows the largest gap, with AMD scoring 146519 against Intel’s 92603, a 58.2 percent advantage. Data compression also favors AMD heavily, with scores of 487145 versus 386591, a 26 percent lead. Extended instruction workloads follow suit, with AMD ahead by 23.6 percent. The AMD part also wins multithreaded PassMark (41737 vs 38298, 9 percent), random string sorting (53113 vs 44648, 19 percent), and every single-core Cinebench test, where it holds a consistent 10.8 to 11 percent edge.

The Intel Core Ultra X9 378H takes the remaining workload categories, which are more specialized. Its PassMark floating point math score of 114500 is 20.9 percent higher than AMD’s 90594, indicating a strong FPU pipeline. The Intel chip also wins PassMark physics with 3404 points versus 2761, an 18.9 percent margin, and data encryption with 29840 versus 25097, a 15.9 percent lead. The Intel part’s single-thread PassMark score of 4453 beats AMD’s 4028 by 9.5 percent, and it wins the prime number finding test with 357 versus 316, an 11.5 percent advantage. These results indicate the Intel architecture excels in workloads that rely on floating-point throughput, cryptographic operations, and certain latency-sensitive single-thread tasks.

Architecture Differences

The two processors use fundamentally different silicon. The AMD Ryzen AI Max 390 is built on TSMC’s 4 nm process and uses the Zen 5 architecture under the Strix Halo codename. It contains 12 cores and 24 threads, with a base clock of 3.20 GHz and a boost clock of 5.00 GHz. The Intel Core Ultra X9 378H is fabricated on Intel’s 3 nm process and uses the Panther Lake-H design under the Panther Lake codename. It has 16 cores but only 16 threads, meaning no simultaneous multithreading, with a base clock of 2.00 GHz and the same 5.00 GHz boost clock.

Cache configurations differ substantially. AMD provides 80 KB of L1 per core, 1 MB of L2 per core, and a large 64 MB shared L3 pool. Intel offers 192 KB of L1 per core, 2.5 MB of L2 per core, but only 18 MB of shared L3. The AMD chip’s larger L3 is likely a contributor to its strong integer and compression results. The die layout also contrasts, with AMD using a dual-die design totaling 2x 70.6 mm², while Intel’s die size is not recorded.

Memory subsystems diverge as well. Both support LPDDR5X, but AMD uses a quad-channel interface providing 256.0 GB/s of bandwidth, while Intel uses dual-channel with 153.6 GB/s. AMD also enables ECC memory support, which Intel does not. PCIe connectivity differs: AMD offers Gen 4 with 16 lanes (CPU only), while Intel provides Gen 5 with 4 lanes. Integrated graphics are the Radeon 8050S on the AMD side and Arc B390 on the Intel side. TDP ratings show AMD at 55 watts and Intel at 25 watts, which aligns with the AMD part’s larger physical footprint and bandwidth provisioning.

Head-to-Head Benchmarks

The most decisive AMD victory comes in PassMark integer math, where the Ryzen AI Max 390 scores 146519 against 92603, a 58.2 percent delta. This is the single largest percentage difference in the dataset. Data compression shows a 26 percent advantage (487145 vs 386591), and extended instructions show 23.6 percent (38716 vs 31315). Random string sorting adds another 19 percent win (53113 vs 44648). Across all Cinebench tests, the AMD part wins by 10.8 percent or 11 percent, including multicore R15 (3635 vs 3281), single-core R15 (513 vs 462), multicore R20 (15146 vs 13672), single-core R20 (2138 vs 1929), multicore R23 (36064 vs 32553), and single-core R23 (5091 vs 4595). The PassMark multithread test shows a narrower 9 percent lead (41737 vs 38298).

The Intel Core Ultra X9 378H answers with strong wins in floating-point math, scoring 114500 versus 90594, a 20.9 percent margin. Physics follows at 18.9 percent (3404 vs 2761). Data encryption shows a 15.9 percent lead (29840 vs 25097). Prime number finding yields an 11.5 percent win (357 vs 316). The PassMark single-thread tests show Intel ahead by 9.5 percent (4453 vs 4028). These wins demonstrate that the Intel part is not merely slower; it has specific strengths in FPU-heavy and cryptographic workloads.

The overall benchmark average confirms the AMD chip’s broader utility. The AMD Ryzen AI Max 390’s average score of 56273 places it 0.5 percent ahead of the AMD Ryzen Threadripper PRO 3955WX and 0.5 percent behind the AMD Ryzen AI 9 HX PRO 470. The Intel Core Ultra X9 378H, with an average of 47468, sits 0.3 percent ahead of the Intel Core i7-13700KF and 0.6 percent behind the Intel Core i9-12900F. These rival comparisons frame both parts as mid-to-high tier mobile processors, with the AMD chip holding a 15.6 percent overall score advantage over the Intel chip.

Specification Differences

The core counts differ: AMD uses 12 cores with 24 threads, while Intel uses 16 cores with 16 threads. Base clocks differ at 3.20 GHz for AMD and 2.00 GHz for Intel, though both boost to 5.00 GHz. TDP ratings show 55 watts for AMD and 25 watts for Intel. The process nodes differ: TSMC 4 nm for AMD and Intel 3 nm for Intel. Caches diverge in every level: L1 is 80 KB per core for AMD and 192 KB per core for Intel; L2 is 1 MB per core for AMD and 2.5 MB per core for Intel; L3 is 64 MB shared for AMD and 18 MB shared for Intel.

Memory bus width differs, with AMD using quad-channel and Intel using dual-channel, leading to bandwidth ratings of 256.0 GB/s and 153.6 GB/s respectively. ECC memory support is present on AMD and absent on Intel. PCIe generation and lane counts differ: Gen 4 with 16 lanes for AMD, Gen 5 with 4 lanes for Intel. Integrated graphics are Radeon 8050S for AMD and Arc B390 for Intel. Sockets are AMD Socket FP11 and Intel BGA 2540. Release dates show AMD launching on 2025-01-05 and Intel on 2026-04-03. The AMD part number is 100-000001423, while Intel’s is unknown. Neither processor has an unlocked multiplier.

FAQ

Q: Which processor has the higher average benchmark score?

A: The AMD Ryzen AI Max 390 has an average benchmark score of 56273, while the Intel Core Ultra X9 378H scores 47468, giving AMD a 15.6 percent overall lead.

Q: How do the two compare in Cinebench R23 multicore?

A: The AMD Ryzen AI Max 390 scores 36064, which is 10.8 percent higher than the Intel Core Ultra X9 378H’s 32553.

Q: In which benchmark does the Intel processor have its largest win?

A: The Intel Core Ultra X9 378H wins PassMark floating point math by 20.9 percent, scoring 114500 against AMD’s 90594.

Q: What is the difference in memory bandwidth?

A: The AMD Ryzen AI Max 390 provides 256.0 GB/s over a quad-channel LPDDR5X interface, while the Intel Core Ultra X9 378H provides 153.6 GB/s over a dual-channel interface.

Q: Does the Intel processor support ECC memory?

A: No, ECC memory is not supported on the Intel Core Ultra X9 378H. The AMD Ryzen AI Max 390 does support ECC memory.

Q: Which part has a higher thread count despite fewer cores?

A: The AMD Ryzen AI Max 390 has 12 cores and 24 threads, while the Intel Core Ultra X9 378H has 16 cores and 16 threads, so AMD offers more threads with fewer physical cores.